© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28184
    Prev
    Next
    INDEX
    Explanations

    employment legal terms

    np_acts-logits-general · gemini-2.5-flash-lite

    avoid sounding repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     -->
    0.43
    𝚋
    0.43
    ◕
    0.41
    ravi
    0.40
     முதலில்
    0.40
     drogas
    0.40
     beige
    0.39
     moelle
    0.38
    రుగులు
    0.38
     प्रतिबि
    0.38
    POSITIVE LOGITS
    闿
    0.49
    広が
    0.46
     تعداد
    0.44
     విషయంలో
    0.44
    ขนาด
    0.42
    Constants
    0.42
     ദേശീയ
    0.42
    年度
    0.41
    線性
    0.41
    ลด
    0.40
    Activations Density 0.001%

    No Known Activations